Pytorch implementation of conditional generative adversarial network (cGAN) using DCGAN architecture for generating 32x32 images of MNIST, SVHN, FashionMNIST, and USPS datasets.
Run commands (also available in scripts.sh):
Dataset | Run command |
---|---|
MNIST | python python main.py --dataset mnist --epochs 10 |
Fashion MNIST | python main.py --dataset fashionmnist --epochs 50 |
SVHN | python main.py --dataset svhn --epochs 100 --n_channels 3 |
USPS | python main.py --dataset usps --epochs 50 |